Preprint · 2017 · Open access
Hyperparameter Optimization: A Spectral Approach
arXiv (Cornell University) · Published 2 June 2017 · DOI 10.48550/arxiv.1706.00764
In brief
“Hyperparameter Optimization: A Spectral Approach” is a 2017 preprint by Elad Hazan and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 133 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 133
- Most cited in
- 2019 (26)
- References
- 40
- Authors
- 3
Abstract
We give a simple, fast algorithm for hyperparameter optimization inspired by techniques from the analysis of Boolean functions. We focus on the high-dimensional regime where the canonical example is training a neural network with a large number of hyperparameters. The algorithm --- an iterative application of compressed sensing techniques for orthogonal polynomials --- requires only uniform sampling of the hyperparameters and is thus easily parallelizable. Experiments for training deep neural networks on Cifar-10 show that compared to state-of-the-art tools (e.g., Hyperband and Spearmint), our algorithm finds significantly improved solutions, in some cases better than what is attainable by hand-tuning. In terms of overall running time (i.e., time required to sample various settings of hyperparameters plus additional computation time), we are at least an order of magnitude faster than Hyperband and Bayesian Optimization. We also outperform Random Search 8x. Additionally, our method comes with provable guarantees and yields the first improvements on the sample complexity of learning decision trees in over two decades. In particular, we obtain the first quasi-polynomial time algorithm for learning noisy decision trees with polynomial sample complexity.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Hazan, E., Klivans, A. R., & Yang, Y. (2017). Hyperparameter Optimization: A Spectral Approach. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1706.00764
MLA 9
Hazan, Elad, et al. “Hyperparameter Optimization: A Spectral Approach.” arXiv (Cornell University), 2017. https://doi.org/10.48550/arxiv.1706.00764.
Chicago
Hazan, Elad, Adam R. Klivans, and Yuan Yang. 2017. “Hyperparameter Optimization: A Spectral Approach.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1706.00764.
Harvard
Hazan, E., Klivans, A. R. and Yang, Y. (2017) ‘Hyperparameter Optimization: A Spectral Approach’, arXiv (Cornell University). doi:10.48550/arxiv.1706.00764.
IEEE
E. Hazan, A. R. Klivans, and Y. Yang, “Hyperparameter Optimization: A Spectral Approach,” arXiv (Cornell University), 2017, doi: 10.48550/arxiv.1706.00764.
BibTeX
@misc{hazan2017hyperparameter,
title = {{Hyperparameter Optimization: A Spectral Approach}},
author = {Hazan, Elad and Klivans, Adam R. and Yang, Yuan},
howpublished = {arXiv (Cornell University)},
year = {2017},
doi = {10.48550/arxiv.1706.00764},
url = {https://doi.org/10.48550/arxiv.1706.00764}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2017 | 1 | |
| 2018 | 7 | |
| 2019 | 26 | |
| 2020 | 15 | |
| 2021 | 8 | |
| 2022 | 17 | |
| 2023 | 24 | |
| 2024 | 13 | |
| 2025 | 17 | |
| 2026 | 5 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- hyperparameter optimization
- spectral methods
- compressed sensing
- orthogonal polynomials
- neural network training
- uniform sampling
- decision tree induction
- sample complexity
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Hazan, E., Klivans, A. R., & Yang, Y. (2017). Hyperparameter Optimization: A Spectral Approach. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1706.00764
How many times has this paper been cited?
133 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Elad Hazan, Adam R. Klivans, Yuan Yang.
What is the DOI of this paper?
10.48550/arxiv.1706.00764, permanently at https://doi.org/10.48550/arxiv.1706.00764. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.